Multimodal Agent MemorySubmit a paper

StreamMind

StreamArena: Toward Continuous, Interactive, and Long-Horizon Agentic Streaming Video Understanding

Xichen Zhang, Guankai Li, Yinghao Zhu, Shijian Wang, Sitong Wu, Shaozuo Yu, et al. · 2026-08-06

Read the paperPDF

Management
T2 Dynamic Memory
Memory changes during deployment through a stable management policy.
Primary modality
Video & streaming
Also: Image, audio, text
Representation
Hybrid
Distinct operative representation paths are explicitly linked for downstream retrieval, reasoning, or control.

How experience becomes memory

Each path is one memory component, traced from what is stored to how it is found again.

  1. persistent audiovisual evidence

    1. Represented asRetained perceptual source evidenceSource- and modality-specific
    2. Stored inHierarchical multi-tier store
    3. Retrieved byMetadata / spatiotemporal retrieval, Planner / tool-assisted retrieval
    4. Source evidenceSource directly available
    Backend workers asynchronously build persistent evidence memory.Full paper: Memory Bank · PDF p. 5 · Figure 1

  2. reusable event records

    1. Represented asPerception-to-text records & summariesCross-represented explicit
    2. Stored inHierarchical multi-tier store
    3. Retrieved bySimilarity search, Planner / tool-assisted retrieval
    4. Source evidenceSource linked & recoverable
    Historical records are reused instead of rebuilt for each query.Full-paper method / memory representation and retrieval · PDF p. 2 · Figure 1

How memory changes (T2 operations)

  • Update · Rule-based update

    During operation, StreamMind applies fixed-rule insertion or replacement to persistent audiovisual evidence; the memory state changes while the governing update policy remains fixed.

  • Consolidation · Episodic / hierarchical summarization

    Fixed backend workers condense stream history. For StreamMind, this specifically supports episodic or hierarchical summarization of persistent audiovisual evidence.

  • Reorganization · Relinking & reindexing

    During operation, StreamMind applies relinking or reindexing of stored items to persistent audiovisual evidence; the memory state changes while the governing update policy remains fixed.

Related systems